Skip to main content

Head-to-head comparison

GPT Image 1.5 vs. Wan 2.6 Text to Image

Compare shared capability tests, arena scores with documented retrieval dates, task-specific image pricing, and verified specifications. Research benchmarks, preference arenas, and our n = 1 samples remain separate.

shared result series
25
shared sample prompts
4
latest arena retrieval
2026-09-22

Change image model selection

Specifications and cost

General specifications and task-specific pricing

A model can have one price for generating new images and another for editing. Prices therefore remain tied to the corresponding arena configuration.

Specifications and pricing for GPT Image 1.5 and Wan 2.6 Text to Image
AttributeGPT Image 1.5Wan 2.6 Text to Image
ProviderOpenAIAlibaba
ReleasedDecember 2025January 2026
AccessAPI, Web appAPI
LifecycleMarked as deprecated by OpenAI; removed from the API on December 1, 2026 Status sourceNo separate lifecycle notice
WeightsProprietaryProprietary
ParametersNot publishedNot published
Maximum output1,536 × 1,024 pixels2K
Arena configurationHighText to Image
Text-to-image price$133 per 1,000 images$30 per 1,000 images
Editing price$133 per 1,000 imagesNo arena entry
Technical sourceModel sourceVerified 2026-08-15Model sourceVerified 2026-08-15
GPT Image 1.5Wan 2.6 Text to Image
Text to Image ArenaUSD per 1,000 images at 1,024 × 1,024 pixels
GPT Image 1.5$133
Wan 2.6 Text to ImageLower price$30

Key to the marks:better valuebetter, but not conclusivetie

Prompt adherence and specialist tests

Shared capability benchmarks

Both checkpoints completed the same four Gradually sample tasks. For each task, 30 archived first outputs are ranked in three differently ordered, model-blind passes. The published 0-100 value normalizes the mean rank. It must still be read as an n = 1 sample per model. This pair also shares 12 results from published research benchmarks.

GPT Image 1.5Wan 2.6 Text to Image
Gradually sample test: Typography and layoutMean of three blind ranks across all 30 first outputs, n = 1 each
GPT Image 1.5Higher blind-rank score29.9 / 100
Wan 2.6 Text to Image13.8 / 100
Gradually sample test: Product photographyMean of three blind ranks across all 30 first outputs, n = 1 each
GPT Image 1.5Higher blind-rank score43.7 / 100
Wan 2.6 Text to Image14.9 / 100
Gradually sample test: Character and detailMean of three blind ranks across all 30 first outputs, n = 1 each
GPT Image 1.577 / 100
Wan 2.6 Text to ImageHigher blind-rank score88.5 / 100
Gradually sample test: InfographicMean of three blind ranks across all 30 first outputs, n = 1 each
GPT Image 1.542.5 / 100
Wan 2.6 Text to ImageHigher blind-rank score48.3 / 100

Key to the marks:better valuebetter, but not conclusivetie

Capability benchmark scores for GPT Image 1.5 and Wan 2.6 Text to Image
BenchmarkGPT Image 1.5Wan 2.6 Text to Image
GEBench Chinese, single-step
Higher benchmark score83.79 / 100
64.2 / 100
GEBench Chinese, multi-step
Higher benchmark score56.97 / 100
50.11 / 100
GEBench Chinese, fictional app
Higher benchmark score60.11 / 100
52.72 / 100
GEBench Chinese, real app
Higher benchmark score55.65 / 100
50.4 / 100
GEBench Chinese, grounding
53.33 / 100
Higher benchmark score59.58 / 100
GEBench Chinese, overall
Higher benchmark score63.22 / 100
55.4 / 100
GEBench English, single-step
Higher benchmark score80.8 / 100
60.17 / 100
GEBench English, multi-step
Higher benchmark score58.87 / 100
44.36 / 100
GEBench English, fictional app
Higher benchmark score63.68 / 100
49.55 / 100
GEBench English, real app
Higher benchmark score58.93 / 100
44.8 / 100
GEBench English, grounding
49.23 / 100
Higher benchmark score53.36 / 100
GEBench English, overall
Higher benchmark score63.16 / 100
50.45 / 100
Gradually sample test: Typography and layout
Higher blind-rank score29.9 / 100
Mean rank: 21.33 (23 / 22 / 19)
Five rubric scores
Headline: 1.67 / 2
Subline: 1.67 / 2
Text control: 1.67 / 2
Visual brief: 1.33 / 2
Layout: 1 / 2
13.8 / 100
Mean rank: 26 (26 / 26 / 26)
Five rubric scores
Headline: 1 / 2
Subline: 1.67 / 2
Text control: 1 / 2
Visual brief: 1.67 / 2
Layout: 1 / 2
Gradually sample test: Product photography
Higher blind-rank score43.7 / 100
Mean rank: 17.33 (22 / 8 / 22)
Five rubric scores
Subject: 1.67 / 2
Time: 1 / 2
Watch details: 1.67 / 2
Photography: 1.67 / 2
Exclusions: 1.67 / 2
14.9 / 100
Mean rank: 25.67 (25 / 26 / 26)
Five rubric scores
Subject: 1.67 / 2
Time: 1.67 / 2
Watch details: 1.67 / 2
Photography: 1.33 / 2
Exclusions: 1.33 / 2
Gradually sample test: Character and detail
77 / 100
Mean rank: 7.67 (6 / 5 / 12)
Five rubric scores
Scene: 1 / 2
Wardrobe: 1 / 2
Anatomy: 1 / 2
Props: 1 / 2
Environment: 1 / 2
Higher blind-rank score88.5 / 100
Mean rank: 4.33 (1 / 9 / 3)
Five rubric scores
Scene: 1 / 2
Wardrobe: 1 / 2
Anatomy: 1 / 2
Props: 1 / 2
Environment: 1 / 2
Gradually sample test: Infographic
42.5 / 100
Mean rank: 17.67 (20 / 14 / 19)
Five rubric scores
Title: 1.67 / 2
Sequence: 1.67 / 2
Labels: 1 / 2
Diagram: 1.67 / 2
Clarity: 1 / 2
Higher blind-rank score48.3 / 100
Mean rank: 16 (14 / 18 / 16)
Five rubric scores
Title: 1.67 / 2
Sequence: 1.67 / 2
Labels: 1 / 2
Diagram: 1.67 / 2
Clarity: 1 / 2

Key to the marks:better valuebetter, but not conclusivetie

Independent preference tests

Shared arena benchmarks

Artificial Analysis and Arena derive scores from blind comparisons. Raters see outputs for the same prompt and choose the image they prefer. Separate series cover text rendering, photorealism, portraits, art, commercial design, and image editing. Confidence intervals indicate how certain a measured lead is.

9 shared result series
GPT Image 1.5Wan 2.6 Text to Image
Text to Image ArenaBlind preference from the same prompt, higher is better
GPT Image 1.5Higher score1,102 Elo
Wan 2.6 Text to Image1,013 Elo
LMArena Text to Image: 3D modelingBlind preference from the same prompt, higher is better
GPT Image 1.5Higher score1,214.044
Wan 2.6 Text to Image1,146.23
LMArena Text to Image: ArtBlind preference from the same prompt, higher is better
GPT Image 1.5Higher score1,224.786
Wan 2.6 Text to Image1,159.207
LMArena Text to Image: CartoonBlind preference from the same prompt, higher is better
GPT Image 1.5Higher score1,245.019
Wan 2.6 Text to Image1,146.213
LMArena Text to Image: Commercial designBlind preference from the same prompt, higher is better
GPT Image 1.5Higher score1,240.235
Wan 2.6 Text to Image1,147.938
LMArena Text to Image: OverallBlind preference from the same prompt, higher is better
GPT Image 1.5Higher score1,239.16
Wan 2.6 Text to Image1,136.586
LMArena Text to Image: PhotorealismBlind preference from the same prompt, higher is better
GPT Image 1.5Higher score1,249.33
Wan 2.6 Text to Image1,128.939
LMArena Text to Image: PortraitsBlind preference from the same prompt, higher is better
GPT Image 1.5Higher score1,261.708
Wan 2.6 Text to Image1,123.606
LMArena Text to Image: Text renderingBlind preference from the same prompt, higher is better
GPT Image 1.5Higher score1,253.437
Wan 2.6 Text to Image1,148.597

Key to the marks:better valuebetter, but not conclusivetie

Arena benchmark scores for GPT Image 1.5 and Wan 2.6 Text to Image
BenchmarkGPT Image 1.5Wan 2.6 Text to ImageSource
Text to Image Arena
Higher score1,102 Elo
Rank 9, 95% confidence interval: ±9, 14,748 ratings
1,013 Elo
Rank 31, 95% confidence interval: ±9, 5,197 ratings
Artificial AnalysisRetrieved 2026-09-22
LMArena Text to Image: 3D modeling
Higher score1,214.044
Rank 15, 95% confidence interval: ±6.6, 15,526 ratings
1,146.23
Rank 34, 95% confidence interval: ±6.22, 19,059 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Art
Higher score1,224.786
Rank 14, 95% confidence interval: ±5.9, 21,424 ratings
1,159.207
Rank 30, 95% confidence interval: ±5.69, 25,966 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Cartoon
Higher score1,245.019
Rank 14, 95% confidence interval: ±4.72, 59,294 ratings
1,146.213
Rank 33, 95% confidence interval: ±4.36, 80,740 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Commercial design
Higher score1,240.235
Rank 14, 95% confidence interval: ±4.6, 58,887 ratings
1,147.938
Rank 34, 95% confidence interval: ±4.26, 75,048 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Overall
Higher score1,239.16
Rank 15, 95% confidence interval: ±3.24, 151,702 ratings
1,136.586
Rank 38, 95% confidence interval: ±2.94, 201,108 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Photorealism
Higher score1,249.33
Rank 15, 95% confidence interval: ±4.7, 60,842 ratings
1,128.939
Rank 43, 95% confidence interval: ±4.28, 81,875 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Portraits
Higher score1,261.708
Rank 12, 95% confidence interval: ±5.81, 29,731 ratings
1,123.606
Rank 47, 95% confidence interval: ±5.18, 44,669 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Text rendering
Higher score1,253.437
Rank 16, 95% confidence interval: ±4.84, 54,527 ratings
1,148.597
Rank 33, 95% confidence interval: ±4.4, 71,703 ratings
LMArenaRetrieved 2026-09-19

Key to the marks:better valuebetter, but not conclusivetie

Visual comparison

Sample images

Our images complement preference data, but do not replace it. The prompt, request count, and selection rule match. Provider resolution, quality tier, randomness, and prompt processing remain visible limitations, so this is not a fully controlled laboratory test.

Largely standardized comparison protocol. Both models receive the same archived prompt, exactly one request, and the first result counts. Files are normalized to 1,024 × 1,024 pixels without cropping. Provider resolution, randomness, quality tier, and prompt processing can still differ. These images are a practical visual test, not a reconstruction of the arena configuration.

Character and detail

Anatomy, clothing, and spatial consistency

Wan 2.6 Text to Image, Character and detail
GPT Image 1.5, Character and detail
GPT Image 1.5
Wan 2.6 Text to Image
Prompt and settings

Create a square cinematic full-body portrait of a fictional bicycle courier waiting under a transparent umbrella at a rainy tram stop in Hamburg at blue hour. She wears a mustard raincoat, navy trousers, red sneakers, a silver helmet, and carries a teal messenger bag. Keep both hands visible, render the bicycle correctly, use realistic wet-street reflections, and include no readable brand names.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 12:17 PM. Source
Wan 2.6 Text to Image. Provider Together, requested 1280x1280, stored 1024x1024 (Lanczos3 downscale), n=1, seed=provider random, provider default steps, model ID Wan-AI/Wan2.6-image, generated Aug 14, 2026, 12:30 PM. Source

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

GPT Image 1.5, image SHA 256: 0dff52ccd39400ac66ac8870c9ea937512ff1474688e70118688f420c38c2296

GPT Image 1.5, request SHA 256: 5199631ac6ff07633dd2fb6ab61c918c26e1e02f37e6131828072233ac04527d

Wan 2.6 Text to Image, image SHA 256: cf49d7136a442f4f1c1ae29af99e917aa83bcbf501fdacfe3a13a3b3e74d7f9a

Wan 2.6 Text to Image, request SHA 256: 10c9f29d46b749448e574d11b560a2c20065d9026f1f52a99f09b23b6299c9c5

Infographic

Numbers, labels, and visual organization

Wan 2.6 Text to Image, Infographic
GPT Image 1.5, Infographic
GPT Image 1.5
Wan 2.6 Text to Image
Prompt and settings

Create a square German infographic titled SO FUNKTIONIERT PHOTOSYNTHESE. Show exactly four numbered steps in this order: 1 LICHT, 2 WASSER, 3 CO₂, 4 ZUCKER + SAUERSTOFF. Use a clean editorial science style with one plant cross-section, simple arrows, high contrast, legible labels, and no other text.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 12:17 PM. Source
Wan 2.6 Text to Image. Provider Together, requested 1280x1280, stored 1024x1024 (Lanczos3 downscale), n=1, seed=provider random, provider default steps, model ID Wan-AI/Wan2.6-image, generated Aug 14, 2026, 12:30 PM. Source

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

GPT Image 1.5, image SHA 256: 1c9ff59c32621c8b48b002dacb0ae66487262280c7c0a5b3d6456c81b248ebe9

GPT Image 1.5, request SHA 256: 7f1efc9531f1e6bed7d61a11c637add9fd892001aea2bb2781f8d89c79a2eb03

Wan 2.6 Text to Image, image SHA 256: 28eecbf460194ec047237c35415d934929baee9de9938bdff435cd21a4416435

Wan 2.6 Text to Image, request SHA 256: d9e00f8c778897df69e719c5bf9fa73115d87abeb23d63eec50dc2280f0e29a9

Product photography

Materials, reflections, and fine details

Wan 2.6 Text to Image, Product photography
GPT Image 1.5, Product photography
GPT Image 1.5
Wan 2.6 Text to Image
Prompt and settings

Create a square premium product photograph of a brushed titanium wristwatch standing upright on dark green marble. The watch has a cream dial, thin black hands set to 10:10, twelve distinct hour markers, a realistic crown, and a dark brown leather strap. Soft window light from the left, controlled reflections, shallow depth of field, no text, no logo, no extra objects.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 12:16 PM. Source
Wan 2.6 Text to Image. Provider Together, requested 1280x1280, stored 1024x1024 (Lanczos3 downscale), n=1, seed=provider random, provider default steps, model ID Wan-AI/Wan2.6-image, generated Aug 14, 2026, 12:29 PM. Source

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

GPT Image 1.5, image SHA 256: 67cfa2f324447027ceb5f82e9446d40a1395b46ce425890a74606b4d97731cf6

GPT Image 1.5, request SHA 256: c850843a298631a4076c5d2686de8e9d7223534f2b8ca53505f437862718bef9

Wan 2.6 Text to Image, image SHA 256: e8dbcfd0ce965814d72d676eddf74f723d476c1f78c5928c7b6efbc4eca4765e

Wan 2.6 Text to Image, request SHA 256: d1539f1db265e5a110b20b8585984ef534d0b89f51e83fd0fc51551832b669d1

Typography and layout

Legible text, hierarchy, and composition

Wan 2.6 Text to Image, Typography and layout
GPT Image 1.5, Typography and layout
GPT Image 1.5
Wan 2.6 Text to Image
Prompt and settings

Create a square editorial poster for an imaginary night train called MONDFALTER. Show the exact German headline MONDFALTER and the exact subline BERLIN NACH LISSABON. Use a restrained midnight-blue and warm-cream palette, one stylized moth, strong Swiss-grid typography, generous negative space, and no additional words or logos.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 1:59 PM. Source
Wan 2.6 Text to Image. Provider Together, requested 1280x1280, stored 1024x1024 (Lanczos3 downscale), n=1, seed=provider random, provider default steps, model ID Wan-AI/Wan2.6-image, generated Aug 14, 2026, 2:01 PM. Source

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

GPT Image 1.5, image SHA 256: 6a4cec86850fd371b65274198e2bf630b3cf36a096f9fb953d4bfe17c3222ebe

GPT Image 1.5, request SHA 256: 9c3a396aecfcaae3f8a25edbe5c8c44d0d33199d7ba29efda864d2b0221c3250

Wan 2.6 Text to Image, image SHA 256: 7e9557478ee297369d7680b31ab3b23a13c984981c0e0c922ef07372999122a7

Wan 2.6 Text to Image, request SHA 256: 2018571c876690a189c5076c520f09d03dd75a18ad6c52550cd51f854c30aa9d

How to read this comparison

An Elo score is not a verdict on creativity

A higher arena score means this specific configuration was preferred more often in blind comparisons.

Typography, character consistency, local execution, licensing, and price may matter more to your workload than overall visual appeal.

Prices cover 1,000 images at 1,024 × 1,024 pixels using settings documented by Artificial Analysis. Subscriptions and special rates are excluded.

More matchups

Related image model comparisons

Compare GPT Image 1.5 and Wan 2.6 Text to Image with other important image models under the same evidence rules. Each page shows only exact shared measurements and samples.

View the complete image model comparison